© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12817
    Prev
    Next
    INDEX
    Explanations

    words/phrases around product descriptions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    つく
    -0.54
    ържа
    -0.52
     oma
    -0.52
     gouver
    -0.49
     agré
    -0.49
     Für
    -0.49
     Trevor
    -0.48
    IJ
    -0.48
     tiro
    -0.47
     Seaside
    -0.47
    POSITIVE LOGITS
     MediatR
    0.91
     ExecuteAsync
    0.87
    =$?
    0.77
    hasMoreElements
    0.75
    Spoljašnje
    0.75
    IsMutable
    0.73
     Signalez
    0.73
    ViewFeatures
    0.73
     SwitchCompat
    0.72
    InjectAttribute
    0.71
    Activations Density 0.723%

    No Known Activations